Artificial Intelligence to Identify Retinal Fundus Images, Quality Validation, Laterality Evaluation, Macular Degeneration, and Suspected Glaucoma
Zapata, Miguel Angel ![ORCID Identifier](/img/uab/orcid.ico)
(Optretina)
Royo-Fibla, Dídac ![ORCID Identifier](/img/uab/orcid.ico)
(Optretina)
Font, Octavi (Optretina)
Vela, J. I ![ORCID Identifier](/img/uab/orcid.ico)
(Institut d'Investigació Biomèdica Sant Pau)
Marcantonio, Ivanna (Institut d'Investigació Biomèdica Sant Pau)
Moya-Sánchez, Eduardo Ulises (Universidad Autónoma de Guadalajara)
Sánchez-Pérez, Abraham (Universidad Autónoma de Guadalajara)
Garcia-Gasulla, Dario
(Barcelona Supercomputing Center)
Cortés, Ulises (Universitat Politècnica de Catalunya)
Ayguadé, Eduard (Universitat Politècnica de Catalunya)
Labarta, Jesus (Universitat Politècnica de Catalunya)
Universitat Autònoma de Barcelona
Date: |
2020 |
Abstract: |
To assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON). Five algorithms were designed. Retrospective study from a database of 306,302 images, Optretina's tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity. Determination of retinal fundus image had AUC of 0. 979 with an accuracy of 96% (sensitivity 97. 7%, specificity 92. 4%). Determination of good quality retinal fundus image had AUC of 0. 947, accuracy 91. 8% (sensitivity 96. 9%, specificity 81. 8%). Algorithm for OD/OS had AUC 0. 989, accuracy 97. 4%. AMD had AUC of 0. 936, accuracy 86. 3% (sensitivity 90. 2% specificity 82. 5%), GON had AUC of 0. 863, accuracy 80. 2% (sensitivity 76. 8%, specificity 83. 8%). Deep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity. |
Rights: |
Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. ![Creative Commons](/img/licenses/by-nc.ico) |
Language: |
Anglès |
Document: |
Article ; recerca ; Versió publicada |
Subject: |
Artificial intelligence ;
Retinal diseases ;
Screening ;
Retinal fundus image |
Published in: |
Clinical Ophthalmology (Auckland, N.Z.), Vol. 14 (february 2020) , p. 419-429, ISSN 1177-5483 |
DOI: 10.2147/OPTH.S235751
PMID: 32103888
The record appears in these collections:
Research literature >
UAB research groups literature >
Research Centres and Groups (research output) >
Health sciences and biosciences >
Institut de Recerca Sant PauArticles >
Research articlesArticles >
Published articles
Record created 2022-02-07, last modified 2024-07-24